ResumenEn este trabajo se predice el comportamiento del precio del oro mediante un modelo basado en redes neuronales artificiales (RNA). El objetivo del modelo es predecir los precios de cierre diarios del mercado de Londres, los cuales son tomados como referencia por el Banco central de Colombia. Se estudian varias configuraciones de RNA tipo propagación hacia adelante tomando como variables de entrada las series diarias del índice del dólar estadounidense DXY, el índice SP500, los precios del petróleo y los precios del oro. Se entrenan diferentes estructuras de RNA utilizando la serie histórica de datos, donde una parte de los mismos se utiliza para entrenamiento y la restante para la predicción. Los resultados obtenidos muestran un buen desempeño del modelo tanto en el periodo histórico analizado como en la predicción, encontrando como mejor estructura aquella que utiliza las series de precios diarias del oro, el índice DXY y el índice SP500. Palabras clave: mercados financieros; mercado del oro; redes neuronales; predicción de precios Artificial Neural Networks applied to the Prediction of the Gold Price AbstractGold price prediction using an artificial neural network model (ANN) is proposed in this work. The objective of the model is to predict the daily closing prices in the London market, which are taken as reference prices for the Central Bank of Colombia. Different configurations of type feed-forward ANN are considered using the dollar index DXY, the SP500 index, the daily oil price series, and the daily gold price series, as inputs to the ANN model. A set of ANN structures are trained using the historical series of data, where one portion is used for training and the other portion is used for testing (prediction). The results show good performance of the model both in the analyzed historical period and the predictions, where the best structure includes the daily price series of gold, the DXY index and the SP500 index.
Using the well known "displace, cut and reflect" method used to generate disks from given solutions of Einstein field equations, we construct some relativistic models of time dependent thin disks of infinite extension made of a perfect fluid based on the Robertson-Walker metric. Two simple families of models of disks based on Robertson-Walker solutions admitting Matter and Ricci collineations are presented. We obtain disks that are in agreement with all the energy conditions. Key words: general relativity; thin disks; exact solutions; robertsonwalker metric. Highlights• We construct time dependent disks of infinite extension made of a perfect fluid based on the well known Robertson-Walker metric.• The models are interpreted as a disk-like matter distribution made of a perfect fluid with negative pressure or tension immersed in a Robertson-Walker type cosmological model.• The solutions satisfy all the energy conditions. 1 PhD. en Ciencias Naturales, ggarcia@utp.edu.co, Universidad Tecnológica de Pereira, Pereira, Colombia. PhD. en Tecnología Eléctrica, materiales, generación y distribución, egarcia@udea.edu.co, Universidad de Antioquía, Medellín, Colombia. Universidad EAFIT 131|Relativistic models of thin disks immersed in a Robertson-Walker type spacetime Modelos relativistas de discos delgados inmersos en un espacio-tiempo tipo Robertson-WalkerResumen Usando el método de "desplazamiento, corte y reflexión" se construyen algunos modelos relativistas exactas de soluciones que representan discos delgados de extensión infinita, dependientes del tiempo y hechos de un fluido perfecto, basados en la métrica de Robertson-Walker. Se presentan dos familias simples de modelos de discos basados sobre el espacio tiempo de Robertson-Walker que admiten colineaciones de Ricci y de materia. Se obtienen modelos de discos que satisfacen todas las condiciones de energía.Palabras clave: relatividad general; discos delgados; soluciones exactas; métrica de robertson-walker.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.